Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose

Ma, Zhiyuan; Wang, Ping; Gao, Zehui; Wang, Ruobing; Khalighi, Koroush

doi:10.1371/journal.pone.0205872

Cited by 103 publications

(81 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The environments are also used to perform memetic optimisation, where global search, as well as local search improvements, are done using genetic and tabu search algorithms respectively. A stacking approach is used to combine classifiers, so as to synthesise estimate outputs from various neural networks and achieve high levels of accuracy (Ma, Wang, Gao, Wang & Khalighi, 2018). A single outcome is then produced for the neural network ensemble.…”

Section: Methodsmentioning

confidence: 99%

Intelligent Malware Detection Using a Neural Network Ensemble Based on a Hybrid Search Mechanism

Akandwanaho¹,

Kooblal²

2019

Afr. j. inf. commun. (Online)

View full text Add to dashboard Cite

Malware threats have become increasingly dynamic and complex, and, accordingly, artificial intelligence techniques have become the focal point for cybersecurity, as they are viewed as being more suited to tackling modern malware incidents. Specifically, neural networks, with their strong generalisation performance capability, are able to address a wide range of cyber threats. This article outlines the development and testing of a neural network ensemble approach to malware detection, based on a hybrid search mechanism. In this mechanism, the optimising of individual networks is done by an adaptive memetic algorithm with tabu search, which is also used to improve hidden neurons and weights of neural networks. The adaptive memetic algorithm combines global and local search optimisation techniques in order to overcome premature convergence and obtain an optimal search outcome. The results from the testing prove that the proposed method is strongly adaptive and efficient in its detection of a range of malware threats, and that it generates better results than other existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Intelligent Malware Detection Using a Neural Network Ensemble Based on a Hybrid Search Mechanism

Akandwanaho¹,

Kooblal²

2019

Afr. j. inf. commun. (Online)

View full text Add to dashboard Cite

show abstract

“…Determination of correct dosage of therapeutics for treating blood clots is an important aspect in patient management. [33][34][35] However, interindividual dosage variability poses a challenge, whereby incorrect dosing could lead to overwhelming adverse outcomes such as localized or systemic hemorrhage. Some research groups have developed MLbased algorithms for determination of warfarin dosage.…”

Section: Application Of Prediction Models In Therapeutic Dose Estimationmentioning

confidence: 99%

“…Some research groups have developed MLbased algorithms for determination of warfarin dosage. [33][34][35] Warfarin is the most widely used oral anticoagulant and its correct dosage is crucial, as both under-and overdosing could lead to thrombosis and bleeding, respectively. The dosage for an individual depends on clinical factors, demographic variables, and genetic variance.…”

Section: Application Of Prediction Models In Therapeutic Dose Estimationmentioning

confidence: 99%

“…On a similar note, Ma et al ensembled ML algorithms using the stacked generalization approach for estimating warfarin dosage. 35 Their rationale of combining several algorithms, which they identified as their stacked generalization approach, was for maximizing accuracy, as using single algorithms have their own limitations. The prediction performance of single algorithms may reach an upper limit even with optimal parameters.…”

Section: Application Of Prediction Models In Therapeutic Dose Estimationmentioning

confidence: 99%

“…The novel regression model used in their study combined the advantages of distinct ML algorithm and significantly improved the prediction accuracy of warfarin dosage compared with other pharmacogenetic models based on single algorithms. 35 The analysis of their algorithm based on stacked generalization frameworks compared with multivariate linear regression (MLR) model revealed a significant improvement in terms of lower value of MAE. The MAE for predicting therapeutic dose of warfarin by MLR in this study was 8.53 mg/week (95% confidence interval [CI]: 8.08-8.99), while the MAE for predicting therapeutic dose of warfarin using their stacked generalization approach was 8.31 mg/week (95% CI: 7.86-8.76).…”

Section: Application Of Prediction Models In Therapeutic Dose Estimationmentioning

confidence: 99%

See 2 more Smart Citations

Using Artificial Intelligence to Manage Thrombosis Research, Diagnosis, and Clinical Management

Mishra

Ashraf

2019

Semin Thromb Hemost

View full text Add to dashboard Cite

Thrombosis development in either arterial or venous system remains a major cause of death and disability worldwide. This poorly controlled in vivo clotting could result in many severe complications including myocardial infarction, venous thromboembolism, stroke, and cerebral venous thrombosis, to name a few. These conditions are collectively known as thromboembolic disorders (TEDs). Appropriate understanding of TEDs is challenging, as they are multifactorial and involve several and often different risk factors. Hence, it requires a collective effort and data from numerous research studies to fully comprehend molecular mechanisms for prediction, prevention, treatment, and overall management of these conditions. To accomplish this arduous feat, a comprehensive approach is required that can compile thousands of available experimental data and transform these into more applicable and purposeful findings. Thus, large datasets could be utilized to generate models that could be predictive of how an individual would respond when subjected to any kind of additional risk factors or surgery, hospitalization, etc., or in the presence of some susceptible genetic variations. Artificial intelligence-based methods harness the capabilities of computer software to imitate human behaviors such as language translation, visual perception, and, most importantly, decision making. These emerging tools, if appropriately explored, might assist in processing of large data and tackle the complexities of identifying novel or interesting pathways that could otherwise be hidden due to their enormity. This narrative review attempts to compile the applications of various subfields of artificial intelligence and machine learning in the context of thrombosis research to date. It further reflects on the potential of artificial intelligence in transforming enormous research data into translational application in the form of predictive computational models.

show abstract

Annual forecasting of high‐temperature days in China through grey wolf optimization‐based support vector machine ensemble

Ren

Shi

Sun

2023

Intl Journal of Climatology

View full text Add to dashboard Cite

With the intensification of anthropogenic warming and urbanization, high‐temperature weather poses an enormous threat to socio‐economic and human healthy. However, the studies on annual high‐temperature days forecasting based on machine learning are relatively deficient. This study proposes a support vector machine (SVM) ensemble model based on grey wolf optimization (GWO) to predict annual high‐temperature days in Guangzhou, Shanghai and Beijing of China. Atmospheric circulation indices during 1959–2013 were utilized as inputs to train and validate models. The fivefold cross validation was used to expand the sample data and evaluate the performance of the member and ensemble models. The optimal ensemble model for Guangzhou has the highest average R (0.8939) and the lowest average root mean square error (RMSE; 3.3771), followed by the optimal ensemble models for Beijing (0.8871 and 3.6059) and Shanghai (0.7578 and 3.9968). Furthermore, compared with the typical SVM and optimal member models, the average validation RMSE of the optimal ensemble model was improved by 32.6 and 10.0% for Guangzhou, by 29.8 and 9.1% for Shanghai, and by 41.3 and 15.1% for Beijing, respectively. This study demonstrates that the GWO‐based SVM ensemble model can be a promising tool for annual high‐temperature days forecasting due to the nonlinear fitting power of the SVM, the hyperparameters tuning capability of the GWO algorithm, and the integration ability of ensemble learning.

show abstract

Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose

Cited by 103 publications

References 26 publications

Intelligent Malware Detection Using a Neural Network Ensemble Based on a Hybrid Search Mechanism

Intelligent Malware Detection Using a Neural Network Ensemble Based on a Hybrid Search Mechanism

Using Artificial Intelligence to Manage Thrombosis Research, Diagnosis, and Clinical Management

Annual forecasting of high‐temperature days in China through grey wolf optimization‐based support vector machine ensemble

Contact Info

Product

Resources

About